论文标题
CCHARMONY：基于颜色检查的图像协调数据集
CcHarmony: Color-checker based Image Harmonization Dataset
论文作者
论文摘要
图像协调目标可以在复合图像中调整前景，以使其与背景兼容，从而产生更真实和和谐的图像。训练深层图像协调网络需要大量的训练数据，但是获取复合图像和地面和谐图像的训练对非常困难。因此，现有的作品转弯以在真实图像中调整前景外观以创建合成的复合图像。但是，这种调整可能无法忠实地反映前景的自然照明变化。在这项工作中，我们探讨了一种构建图像协调数据集的新型及传递方式。具体而言，基于带有记录的照明信息的现有数据集，我们首先将前景转换为真实图像的标准照明条件，然后将其转换为另一个照明条件，该条件与原始背景结合在一起以形成合成的复合图像。通过这种方式，我们构建了一个称为CCHARMONY的图像协调数据集，该数据集以颜色检查器（CC）命名。该数据集可从https://github.com/bcmi/image-harmonization-dataset-ccharmony获得。
Image harmonization targets at adjusting the foreground in a composite image to make it compatible with the background, producing a more realistic and harmonious image. Training deep image harmonization network requires abundant training data, but it is extremely difficult to acquire training pairs of composite images and ground-truth harmonious images. Therefore, existing works turn to adjust the foreground appearance in a real image to create a synthetic composite image. However, such adjustment may not faithfully reflect the natural illumination change of foreground. In this work, we explore a novel transitive way to construct image harmonization dataset. Specifically, based on the existing datasets with recorded illumination information, we first convert the foreground in a real image to the standard illumination condition, and then convert it to another illumination condition, which is combined with the original background to form a synthetic composite image. In this manner, we construct an image harmonization dataset called ccHarmony, which is named after color checker (cc). The dataset is available at https://github.com/bcmi/Image-Harmonization-Dataset-ccHarmony.
